Classification Of Student Depression Using Support Vector Machine Modelling and Backward Elimination
DOI:
https://doi.org/10.30871/jaic.v10i1.12203Keywords:
Backward Elimination, Feature Selection, Machine Learning, Student Depression, Support Vector MachineAbstract
Depression among university students has become a serious mental health concern that can negatively affect academic performance and overall well-being. Early detection of Depression is essential to provide timely support and preventive interventions. This study proposes a machine learning approach to classify student Depression using a Support Vector Machine (SVM) combined with Backward Elimination (BE) for feature selection. The dataset used in this research was obtained from a public repository and consists of 502 student records with multiple psychological and demographic attributes. Data preprocessing included categorical encoding and Min–Max normalization, followed by an 80:20 split for training and testing. Experimental results show that the baseline SVM model achieved an accuracy of 0.9208, while the application of Backward Elimination improved the performance to 0.9604. In addition, precision, recall, and F1-score also showed notable improvements, indicating a reduction in misclassification, particularly for non-depressed students. These findings demonstrate that integrating feature selection with SVM can enhance classification performance and provide a more efficient model for supporting early Depression detection among university students.
Downloads
References
[1] W. H. Organization, “World Mental Health Report 2023,” WHO Press, 2023.
[2] X. Li, Y. Chen, and L. Wang, “Depression Prediction in University Students Using Machine Learning Approaches,” J. Ment. Heal. Informatics, vol. 12, no. 2, pp. 45–58, 2023.
[3] A. Wahdi, S. Wilopo, and H. Erskine, “Indonesia National Adolescent Mental Health Survey 2023,” Indones. J. Ment. Heal., 2023.
[4] B. P. Statistik, “Statistik Pendidikan Tinggi 2023,” BPS, 2023.
[5] R. Wardani and M. Rahman, “Pengaruh Stres Akademik terhadap Depresi Mahasiswa,” J. Psikol., 2023.
[6] R. Alamsyah and D. Putra, “Beban Akademik dan Dampaknya terhadap Kesehatan Mental Mahasiswa,” J. Pendidik., 2022.
[7] F. Anwar, R. Sari, and D. Nugraha, “Hubungan Tekanan Akademik dengan Tingkat Depresi pada Mahasiswa,” J. Psikol. Pendidik., 2022.
[8] T. Hermawan, “Machine Learning Approach for Early Mental Health Detection,” J. Teknol. Inf., 2025.
[9] M. Khan, F. Abdullah, and S. Rahman, “Support Vector Machine Performance in Nonlinear Psychological Data Classification,” Int. J. Behav. Comput., vol. 7, no. 1, pp. 21–34, 2022.
[10] M. Risqi, W. Prastya, and J. Vikri, “Depression Classification Using SVM: A Study on Student Dataset,” J. Inform., 2025.
[11] S. Putri, “Structural Risk Minimization in Modern Machine Learning,” Mach. Learn. Rev., 2023.
[12] L. Guido, “Advances in Computational Mental Health Modeling,” Comput. Psychol. J., 2024.
[13] N. Rakhmawati, A. Taufiq, and F. Maulana, “Backward Elimination for Feature Optimization on Health Data,” J. Ilmu Komput. dan Inf., 2023.
[14] R. Safira and I. Sari, “Improving Health Prediction Accuracy Using Feature Selection,” J. Kesehat. Digit., 2025.
[15] E. P. Efendi, M. A. Barata, and A. D. Ardianti, “Komparasi Metode Svm Dan C4.5 Dengan Backward Elimination Untuk Klasifikasi Stres,” JIKO (Jurnal Inform. dan Komputer), vol. 9, no. 3, p. (Halaman tidak tersedia, mohon periksa PDF)-(Halam, Mar. 2025, [Online]. Available: https://ejournal.akakom.ac.id/index.php/jiko/article/view/2130
[16] A. Susanto, E. Wijaya, and I. Setiawan, “Predictive Analytics for Medical Classification Using SVM,” Bioinforma. Heal. Anal., 2024.
[17] X. Zhang, Y. Liu, and H. Chen, “Social Media-Based Depression Detection Using SVM and Feature Reduction,” ACM Soc. Comput., 2023.
[18] R. Juwita, A. Santoso, and M. Lestari, “Quantitative Approach for Machine Learning Evaluation in Mental Health Research,” J. Data Sci. Appl., vol. 5, no. 2, pp. 112–125, 2023.
[19] T. Nguyen, P. Do, and L. Tran, “Reproducible Machine Learning Pipelines for Healthcare Data,” Healthc. Anal. Rev., vol. 9, no. 4, pp. 201–219, 2022.
[20] A. Aliyev and S. A. Ozel, “Effective Methods of Categorical Data Encoding for Artificial Intelligence Algorithms,” Appl. Sci., vol. 13, no. 16, pp. 1–20, 2023.
[21] D. Putra, R. Wibowo, and L. Sasmita, “The Efficiency of Label Encoding for Margin-Based Models in Machine Learning,” Indones. J. Inf. Syst., vol. 6, no. 1, pp. 33–47, 2024.
[22] T. Handayani, R. Saputra, and S. Miranti, “Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance,” Appl. Data Eng. J., vol. 4, no. 3, pp. 55–66, 2023.
[23] A. Faqih, M. J. Vikri, and I. A. Sa’ida, “Optimizing Gated Recurrent Unit (GRU) for Gold Price Prediction: Hyperparameter Tuning and Model Evaluation on Historical XAU/USD Data,” J. Sisfokom (Sistem Inf. dan Komputer), 2025, [Online]. Available: https://api.semanticscholar.org/CorpusID:278868230
[24] N. Fadlullah, “Normalization Strategies for Machine Learning Stability,” J. Comput. Optim., vol. 9, no. 1, pp. 14–26, 2024.
[25] F. R. A. Harianto, Z. Alawi, and I. A. Sa’ida, “Pengaruh Komposisi Split Data Pada Akurasi Klasifikasi Penderita Diabetes Menggunakan Algoritma Machine Learning,” J. Sist. Inf. dan Inform., 2025, [Online]. Available: https://api.semanticscholar.org/CorpusID:276281557
[26] B. Haryanto, “Kernel RBF Performance on Nonlinear Psychological Pattern Classification,” Comput. Psychol. J., vol. 14, no. 1, pp. 12–25, 2024.
[27] M. Riahi and A. Khelifa, “Hyperparameter Effects on Support Vector Machine Optimization,” Int. J. Mach. Learn. Optim., vol. 11, no. 3, pp. 188–204, 2023.
[28] J. Pardede, R. Silalahi, and M. Naibaho, “Performance Enhancement of SVM Classification Using Backward Elimination,” J. Data Sci. Heal. Anal., vol. 9, no. 2, pp. 77–89, 2021.
[29] S. Aini, H. Darmawan, and P. Yuliana, “Why Accuracy is Not Enough: Evaluation Metrics for Health Classification,” J. Appl. Data Sci., vol. 4, no. 2, pp. 99–115, 2023.
[30] P. R. Group, “Recall as a Clinical Priority Metric for Early Disease Detection,” Polibatam J. Informatics, vol. 3, no. 1, pp. 22–33, 2022.
[31] L. Rochmah, R. Pratama, and S. Fauziah, “F1-Score as the Most Reliable Metric for Imbalanced Biomedical Classification,” Biomed. Comput. Rev., vol. 7, no. 2, pp. 44–59, 2023.
[32] E. F. Laili, Z. Alawi, R. Rohmah, and M. A. Barata, “Komparasi Algoritma Decision Tree Dan Support Vector Machine (Svm) Dalam Klasifikasi Serangan Jantung,” J. Sist. Inf. dan Inform., 2025, [Online]. Available: https://api.semanticscholar.org/CorpusID:276263579
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rohmat Abidin Sabar, Afril Efan Pajri, Jauhara Rana Budiani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
